-
Notifications
You must be signed in to change notification settings - Fork 53.6k
/
shm.c
1879 lines (1625 loc) · 45 KB
/
shm.c
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
// SPDX-License-Identifier: GPL-2.0
/*
* linux/ipc/shm.c
* Copyright (C) 1992, 1993 Krishna Balasubramanian
* Many improvements/fixes by Bruno Haible.
* Replaced `struct shm_desc' by `struct vm_area_struct', July 1994.
* Fixed the shm swap deallocation (shm_unuse()), August 1998 Andrea Arcangeli.
*
* /proc/sysvipc/shm support (c) 1999 Dragos Acostachioaie <[email protected]>
* BIGMEM support, Andrea Arcangeli <[email protected]>
* SMP thread shm, Jean-Luc Boyard <[email protected]>
* HIGHMEM support, Ingo Molnar <[email protected]>
* Make shmmax, shmall, shmmni sysctl'able, Christoph Rohland <[email protected]>
* Shared /dev/zero support, Kanoj Sarcar <[email protected]>
* Move the mm functionality over to mm/shmem.c, Christoph Rohland <[email protected]>
*
* support for audit of ipc object properties and permission changes
* Dustin Kirkland <[email protected]>
*
* namespaces support
* OpenVZ, SWsoft Inc.
* Pavel Emelianov <[email protected]>
*
* Better ipc lock (kern_ipc_perm.lock) handling
* Davidlohr Bueso <[email protected]>, June 2013.
*/
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <linux/shm.h>
#include <uapi/linux/shm.h>
#include <linux/init.h>
#include <linux/file.h>
#include <linux/mman.h>
#include <linux/shmem_fs.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/audit.h>
#include <linux/capability.h>
#include <linux/ptrace.h>
#include <linux/seq_file.h>
#include <linux/rwsem.h>
#include <linux/nsproxy.h>
#include <linux/mount.h>
#include <linux/ipc_namespace.h>
#include <linux/rhashtable.h>
#include <linux/uaccess.h>
#include "util.h"
struct shmid_kernel /* private to the kernel */
{
struct kern_ipc_perm shm_perm;
struct file *shm_file;
unsigned long shm_nattch;
unsigned long shm_segsz;
time64_t shm_atim;
time64_t shm_dtim;
time64_t shm_ctim;
struct pid *shm_cprid;
struct pid *shm_lprid;
struct ucounts *mlock_ucounts;
/*
* The task created the shm object, for
* task_lock(shp->shm_creator)
*/
struct task_struct *shm_creator;
/*
* List by creator. task_lock(->shm_creator) required for read/write.
* If list_empty(), then the creator is dead already.
*/
struct list_head shm_clist;
struct ipc_namespace *ns;
} __randomize_layout;
/* shm_mode upper byte flags */
#define SHM_DEST 01000 /* segment will be destroyed on last detach */
#define SHM_LOCKED 02000 /* segment will not be swapped */
struct shm_file_data {
int id;
struct ipc_namespace *ns;
struct file *file;
const struct vm_operations_struct *vm_ops;
};
#define shm_file_data(file) (*((struct shm_file_data **)&(file)->private_data))
static const struct file_operations shm_file_operations;
static const struct vm_operations_struct shm_vm_ops;
#define shm_ids(ns) ((ns)->ids[IPC_SHM_IDS])
#define shm_unlock(shp) \
ipc_unlock(&(shp)->shm_perm)
static int newseg(struct ipc_namespace *, struct ipc_params *);
static void shm_open(struct vm_area_struct *vma);
static void shm_close(struct vm_area_struct *vma);
static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp);
#ifdef CONFIG_PROC_FS
static int sysvipc_shm_proc_show(struct seq_file *s, void *it);
#endif
void shm_init_ns(struct ipc_namespace *ns)
{
ns->shm_ctlmax = SHMMAX;
ns->shm_ctlall = SHMALL;
ns->shm_ctlmni = SHMMNI;
ns->shm_rmid_forced = 0;
ns->shm_tot = 0;
ipc_init_ids(&shm_ids(ns));
}
/*
* Called with shm_ids.rwsem (writer) and the shp structure locked.
* Only shm_ids.rwsem remains locked on exit.
*/
static void do_shm_rmid(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
{
struct shmid_kernel *shp;
shp = container_of(ipcp, struct shmid_kernel, shm_perm);
WARN_ON(ns != shp->ns);
if (shp->shm_nattch) {
shp->shm_perm.mode |= SHM_DEST;
/* Do not find it any more */
ipc_set_key_private(&shm_ids(ns), &shp->shm_perm);
shm_unlock(shp);
} else
shm_destroy(ns, shp);
}
#ifdef CONFIG_IPC_NS
void shm_exit_ns(struct ipc_namespace *ns)
{
free_ipcs(ns, &shm_ids(ns), do_shm_rmid);
idr_destroy(&ns->ids[IPC_SHM_IDS].ipcs_idr);
rhashtable_destroy(&ns->ids[IPC_SHM_IDS].key_ht);
}
#endif
static int __init ipc_ns_init(void)
{
shm_init_ns(&init_ipc_ns);
return 0;
}
pure_initcall(ipc_ns_init);
void __init shm_init(void)
{
ipc_init_proc_interface("sysvipc/shm",
#if BITS_PER_LONG <= 32
" key shmid perms size cpid lpid nattch uid gid cuid cgid atime dtime ctime rss swap\n",
#else
" key shmid perms size cpid lpid nattch uid gid cuid cgid atime dtime ctime rss swap\n",
#endif
IPC_SHM_IDS, sysvipc_shm_proc_show);
}
static inline struct shmid_kernel *shm_obtain_object(struct ipc_namespace *ns, int id)
{
struct kern_ipc_perm *ipcp = ipc_obtain_object_idr(&shm_ids(ns), id);
if (IS_ERR(ipcp))
return ERR_CAST(ipcp);
return container_of(ipcp, struct shmid_kernel, shm_perm);
}
static inline struct shmid_kernel *shm_obtain_object_check(struct ipc_namespace *ns, int id)
{
struct kern_ipc_perm *ipcp = ipc_obtain_object_check(&shm_ids(ns), id);
if (IS_ERR(ipcp))
return ERR_CAST(ipcp);
return container_of(ipcp, struct shmid_kernel, shm_perm);
}
/*
* shm_lock_(check_) routines are called in the paths where the rwsem
* is not necessarily held.
*/
static inline struct shmid_kernel *shm_lock(struct ipc_namespace *ns, int id)
{
struct kern_ipc_perm *ipcp;
rcu_read_lock();
ipcp = ipc_obtain_object_idr(&shm_ids(ns), id);
if (IS_ERR(ipcp))
goto err;
ipc_lock_object(ipcp);
/*
* ipc_rmid() may have already freed the ID while ipc_lock_object()
* was spinning: here verify that the structure is still valid.
* Upon races with RMID, return -EIDRM, thus indicating that
* the ID points to a removed identifier.
*/
if (ipc_valid_object(ipcp)) {
/* return a locked ipc object upon success */
return container_of(ipcp, struct shmid_kernel, shm_perm);
}
ipc_unlock_object(ipcp);
ipcp = ERR_PTR(-EIDRM);
err:
rcu_read_unlock();
/*
* Callers of shm_lock() must validate the status of the returned ipc
* object pointer and error out as appropriate.
*/
return ERR_CAST(ipcp);
}
static inline void shm_lock_by_ptr(struct shmid_kernel *ipcp)
{
rcu_read_lock();
ipc_lock_object(&ipcp->shm_perm);
}
static void shm_rcu_free(struct rcu_head *head)
{
struct kern_ipc_perm *ptr = container_of(head, struct kern_ipc_perm,
rcu);
struct shmid_kernel *shp = container_of(ptr, struct shmid_kernel,
shm_perm);
security_shm_free(&shp->shm_perm);
kfree(shp);
}
/*
* It has to be called with shp locked.
* It must be called before ipc_rmid()
*/
static inline void shm_clist_rm(struct shmid_kernel *shp)
{
struct task_struct *creator;
/* ensure that shm_creator does not disappear */
rcu_read_lock();
/*
* A concurrent exit_shm may do a list_del_init() as well.
* Just do nothing if exit_shm already did the work
*/
if (!list_empty(&shp->shm_clist)) {
/*
* shp->shm_creator is guaranteed to be valid *only*
* if shp->shm_clist is not empty.
*/
creator = shp->shm_creator;
task_lock(creator);
/*
* list_del_init() is a nop if the entry was already removed
* from the list.
*/
list_del_init(&shp->shm_clist);
task_unlock(creator);
}
rcu_read_unlock();
}
static inline void shm_rmid(struct shmid_kernel *s)
{
shm_clist_rm(s);
ipc_rmid(&shm_ids(s->ns), &s->shm_perm);
}
static int __shm_open(struct shm_file_data *sfd)
{
struct shmid_kernel *shp;
shp = shm_lock(sfd->ns, sfd->id);
if (IS_ERR(shp))
return PTR_ERR(shp);
if (shp->shm_file != sfd->file) {
/* ID was reused */
shm_unlock(shp);
return -EINVAL;
}
shp->shm_atim = ktime_get_real_seconds();
ipc_update_pid(&shp->shm_lprid, task_tgid(current));
shp->shm_nattch++;
shm_unlock(shp);
return 0;
}
/* This is called by fork, once for every shm attach. */
static void shm_open(struct vm_area_struct *vma)
{
struct file *file = vma->vm_file;
struct shm_file_data *sfd = shm_file_data(file);
int err;
/* Always call underlying open if present */
if (sfd->vm_ops->open)
sfd->vm_ops->open(vma);
err = __shm_open(sfd);
/*
* We raced in the idr lookup or with shm_destroy().
* Either way, the ID is busted.
*/
WARN_ON_ONCE(err);
}
/*
* shm_destroy - free the struct shmid_kernel
*
* @ns: namespace
* @shp: struct to free
*
* It has to be called with shp and shm_ids.rwsem (writer) locked,
* but returns with shp unlocked and freed.
*/
static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp)
{
struct file *shm_file;
shm_file = shp->shm_file;
shp->shm_file = NULL;
ns->shm_tot -= (shp->shm_segsz + PAGE_SIZE - 1) >> PAGE_SHIFT;
shm_rmid(shp);
shm_unlock(shp);
if (!is_file_hugepages(shm_file))
shmem_lock(shm_file, 0, shp->mlock_ucounts);
fput(shm_file);
ipc_update_pid(&shp->shm_cprid, NULL);
ipc_update_pid(&shp->shm_lprid, NULL);
ipc_rcu_putref(&shp->shm_perm, shm_rcu_free);
}
/*
* shm_may_destroy - identifies whether shm segment should be destroyed now
*
* Returns true if and only if there are no active users of the segment and
* one of the following is true:
*
* 1) shmctl(id, IPC_RMID, NULL) was called for this shp
*
* 2) sysctl kernel.shm_rmid_forced is set to 1.
*/
static bool shm_may_destroy(struct shmid_kernel *shp)
{
return (shp->shm_nattch == 0) &&
(shp->ns->shm_rmid_forced ||
(shp->shm_perm.mode & SHM_DEST));
}
/*
* remove the attach descriptor vma.
* free memory for segment if it is marked destroyed.
* The descriptor has already been removed from the current->mm->mmap list
* and will later be kfree()d.
*/
static void __shm_close(struct shm_file_data *sfd)
{
struct shmid_kernel *shp;
struct ipc_namespace *ns = sfd->ns;
down_write(&shm_ids(ns).rwsem);
/* remove from the list of attaches of the shm segment */
shp = shm_lock(ns, sfd->id);
/*
* We raced in the idr lookup or with shm_destroy().
* Either way, the ID is busted.
*/
if (WARN_ON_ONCE(IS_ERR(shp)))
goto done; /* no-op */
ipc_update_pid(&shp->shm_lprid, task_tgid(current));
shp->shm_dtim = ktime_get_real_seconds();
shp->shm_nattch--;
if (shm_may_destroy(shp))
shm_destroy(ns, shp);
else
shm_unlock(shp);
done:
up_write(&shm_ids(ns).rwsem);
}
static void shm_close(struct vm_area_struct *vma)
{
struct file *file = vma->vm_file;
struct shm_file_data *sfd = shm_file_data(file);
/* Always call underlying close if present */
if (sfd->vm_ops->close)
sfd->vm_ops->close(vma);
__shm_close(sfd);
}
/* Called with ns->shm_ids(ns).rwsem locked */
static int shm_try_destroy_orphaned(int id, void *p, void *data)
{
struct ipc_namespace *ns = data;
struct kern_ipc_perm *ipcp = p;
struct shmid_kernel *shp = container_of(ipcp, struct shmid_kernel, shm_perm);
/*
* We want to destroy segments without users and with already
* exit'ed originating process.
*
* As shp->* are changed under rwsem, it's safe to skip shp locking.
*/
if (!list_empty(&shp->shm_clist))
return 0;
if (shm_may_destroy(shp)) {
shm_lock_by_ptr(shp);
shm_destroy(ns, shp);
}
return 0;
}
void shm_destroy_orphaned(struct ipc_namespace *ns)
{
down_write(&shm_ids(ns).rwsem);
if (shm_ids(ns).in_use)
idr_for_each(&shm_ids(ns).ipcs_idr, &shm_try_destroy_orphaned, ns);
up_write(&shm_ids(ns).rwsem);
}
/* Locking assumes this will only be called with task == current */
void exit_shm(struct task_struct *task)
{
for (;;) {
struct shmid_kernel *shp;
struct ipc_namespace *ns;
task_lock(task);
if (list_empty(&task->sysvshm.shm_clist)) {
task_unlock(task);
break;
}
shp = list_first_entry(&task->sysvshm.shm_clist, struct shmid_kernel,
shm_clist);
/*
* 1) Get pointer to the ipc namespace. It is worth to say
* that this pointer is guaranteed to be valid because
* shp lifetime is always shorter than namespace lifetime
* in which shp lives.
* We taken task_lock it means that shp won't be freed.
*/
ns = shp->ns;
/*
* 2) If kernel.shm_rmid_forced is not set then only keep track of
* which shmids are orphaned, so that a later set of the sysctl
* can clean them up.
*/
if (!ns->shm_rmid_forced)
goto unlink_continue;
/*
* 3) get a reference to the namespace.
* The refcount could be already 0. If it is 0, then
* the shm objects will be free by free_ipc_work().
*/
ns = get_ipc_ns_not_zero(ns);
if (!ns) {
unlink_continue:
list_del_init(&shp->shm_clist);
task_unlock(task);
continue;
}
/*
* 4) get a reference to shp.
* This cannot fail: shm_clist_rm() is called before
* ipc_rmid(), thus the refcount cannot be 0.
*/
WARN_ON(!ipc_rcu_getref(&shp->shm_perm));
/*
* 5) unlink the shm segment from the list of segments
* created by current.
* This must be done last. After unlinking,
* only the refcounts obtained above prevent IPC_RMID
* from destroying the segment or the namespace.
*/
list_del_init(&shp->shm_clist);
task_unlock(task);
/*
* 6) we have all references
* Thus lock & if needed destroy shp.
*/
down_write(&shm_ids(ns).rwsem);
shm_lock_by_ptr(shp);
/*
* rcu_read_lock was implicitly taken in shm_lock_by_ptr, it's
* safe to call ipc_rcu_putref here
*/
ipc_rcu_putref(&shp->shm_perm, shm_rcu_free);
if (ipc_valid_object(&shp->shm_perm)) {
if (shm_may_destroy(shp))
shm_destroy(ns, shp);
else
shm_unlock(shp);
} else {
/*
* Someone else deleted the shp from namespace
* idr/kht while we have waited.
* Just unlock and continue.
*/
shm_unlock(shp);
}
up_write(&shm_ids(ns).rwsem);
put_ipc_ns(ns); /* paired with get_ipc_ns_not_zero */
}
}
static vm_fault_t shm_fault(struct vm_fault *vmf)
{
struct file *file = vmf->vma->vm_file;
struct shm_file_data *sfd = shm_file_data(file);
return sfd->vm_ops->fault(vmf);
}
static int shm_may_split(struct vm_area_struct *vma, unsigned long addr)
{
struct file *file = vma->vm_file;
struct shm_file_data *sfd = shm_file_data(file);
if (sfd->vm_ops->may_split)
return sfd->vm_ops->may_split(vma, addr);
return 0;
}
static unsigned long shm_pagesize(struct vm_area_struct *vma)
{
struct file *file = vma->vm_file;
struct shm_file_data *sfd = shm_file_data(file);
if (sfd->vm_ops->pagesize)
return sfd->vm_ops->pagesize(vma);
return PAGE_SIZE;
}
#ifdef CONFIG_NUMA
static int shm_set_policy(struct vm_area_struct *vma, struct mempolicy *mpol)
{
struct shm_file_data *sfd = shm_file_data(vma->vm_file);
int err = 0;
if (sfd->vm_ops->set_policy)
err = sfd->vm_ops->set_policy(vma, mpol);
return err;
}
static struct mempolicy *shm_get_policy(struct vm_area_struct *vma,
unsigned long addr, pgoff_t *ilx)
{
struct shm_file_data *sfd = shm_file_data(vma->vm_file);
struct mempolicy *mpol = vma->vm_policy;
if (sfd->vm_ops->get_policy)
mpol = sfd->vm_ops->get_policy(vma, addr, ilx);
return mpol;
}
#endif
static int shm_mmap(struct file *file, struct vm_area_struct *vma)
{
struct shm_file_data *sfd = shm_file_data(file);
int ret;
/*
* In case of remap_file_pages() emulation, the file can represent an
* IPC ID that was removed, and possibly even reused by another shm
* segment already. Propagate this case as an error to caller.
*/
ret = __shm_open(sfd);
if (ret)
return ret;
ret = call_mmap(sfd->file, vma);
if (ret) {
__shm_close(sfd);
return ret;
}
sfd->vm_ops = vma->vm_ops;
#ifdef CONFIG_MMU
WARN_ON(!sfd->vm_ops->fault);
#endif
vma->vm_ops = &shm_vm_ops;
return 0;
}
static int shm_release(struct inode *ino, struct file *file)
{
struct shm_file_data *sfd = shm_file_data(file);
put_ipc_ns(sfd->ns);
fput(sfd->file);
shm_file_data(file) = NULL;
kfree(sfd);
return 0;
}
static int shm_fsync(struct file *file, loff_t start, loff_t end, int datasync)
{
struct shm_file_data *sfd = shm_file_data(file);
if (!sfd->file->f_op->fsync)
return -EINVAL;
return sfd->file->f_op->fsync(sfd->file, start, end, datasync);
}
static long shm_fallocate(struct file *file, int mode, loff_t offset,
loff_t len)
{
struct shm_file_data *sfd = shm_file_data(file);
if (!sfd->file->f_op->fallocate)
return -EOPNOTSUPP;
return sfd->file->f_op->fallocate(file, mode, offset, len);
}
static unsigned long shm_get_unmapped_area(struct file *file,
unsigned long addr, unsigned long len, unsigned long pgoff,
unsigned long flags)
{
struct shm_file_data *sfd = shm_file_data(file);
return sfd->file->f_op->get_unmapped_area(sfd->file, addr, len,
pgoff, flags);
}
static const struct file_operations shm_file_operations = {
.mmap = shm_mmap,
.fsync = shm_fsync,
.release = shm_release,
.get_unmapped_area = shm_get_unmapped_area,
.llseek = noop_llseek,
.fallocate = shm_fallocate,
};
/*
* shm_file_operations_huge is now identical to shm_file_operations,
* but we keep it distinct for the sake of is_file_shm_hugepages().
*/
static const struct file_operations shm_file_operations_huge = {
.mmap = shm_mmap,
.fsync = shm_fsync,
.release = shm_release,
.get_unmapped_area = shm_get_unmapped_area,
.llseek = noop_llseek,
.fallocate = shm_fallocate,
};
bool is_file_shm_hugepages(struct file *file)
{
return file->f_op == &shm_file_operations_huge;
}
static const struct vm_operations_struct shm_vm_ops = {
.open = shm_open, /* callback for a new vm-area open */
.close = shm_close, /* callback for when the vm-area is released */
.fault = shm_fault,
.may_split = shm_may_split,
.pagesize = shm_pagesize,
#if defined(CONFIG_NUMA)
.set_policy = shm_set_policy,
.get_policy = shm_get_policy,
#endif
};
/**
* newseg - Create a new shared memory segment
* @ns: namespace
* @params: ptr to the structure that contains key, size and shmflg
*
* Called with shm_ids.rwsem held as a writer.
*/
static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
{
key_t key = params->key;
int shmflg = params->flg;
size_t size = params->u.size;
int error;
struct shmid_kernel *shp;
size_t numpages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
struct file *file;
char name[13];
vm_flags_t acctflag = 0;
if (size < SHMMIN || size > ns->shm_ctlmax)
return -EINVAL;
if (numpages << PAGE_SHIFT < size)
return -ENOSPC;
if (ns->shm_tot + numpages < ns->shm_tot ||
ns->shm_tot + numpages > ns->shm_ctlall)
return -ENOSPC;
shp = kmalloc(sizeof(*shp), GFP_KERNEL_ACCOUNT);
if (unlikely(!shp))
return -ENOMEM;
shp->shm_perm.key = key;
shp->shm_perm.mode = (shmflg & S_IRWXUGO);
shp->mlock_ucounts = NULL;
shp->shm_perm.security = NULL;
error = security_shm_alloc(&shp->shm_perm);
if (error) {
kfree(shp);
return error;
}
sprintf(name, "SYSV%08x", key);
if (shmflg & SHM_HUGETLB) {
struct hstate *hs;
size_t hugesize;
hs = hstate_sizelog((shmflg >> SHM_HUGE_SHIFT) & SHM_HUGE_MASK);
if (!hs) {
error = -EINVAL;
goto no_file;
}
hugesize = ALIGN(size, huge_page_size(hs));
/* hugetlb_file_setup applies strict accounting */
if (shmflg & SHM_NORESERVE)
acctflag = VM_NORESERVE;
file = hugetlb_file_setup(name, hugesize, acctflag,
HUGETLB_SHMFS_INODE, (shmflg >> SHM_HUGE_SHIFT) & SHM_HUGE_MASK);
} else {
/*
* Do not allow no accounting for OVERCOMMIT_NEVER, even
* if it's asked for.
*/
if ((shmflg & SHM_NORESERVE) &&
sysctl_overcommit_memory != OVERCOMMIT_NEVER)
acctflag = VM_NORESERVE;
file = shmem_kernel_file_setup(name, size, acctflag);
}
error = PTR_ERR(file);
if (IS_ERR(file))
goto no_file;
shp->shm_cprid = get_pid(task_tgid(current));
shp->shm_lprid = NULL;
shp->shm_atim = shp->shm_dtim = 0;
shp->shm_ctim = ktime_get_real_seconds();
shp->shm_segsz = size;
shp->shm_nattch = 0;
shp->shm_file = file;
shp->shm_creator = current;
/* ipc_addid() locks shp upon success. */
error = ipc_addid(&shm_ids(ns), &shp->shm_perm, ns->shm_ctlmni);
if (error < 0)
goto no_id;
shp->ns = ns;
task_lock(current);
list_add(&shp->shm_clist, ¤t->sysvshm.shm_clist);
task_unlock(current);
/*
* shmid gets reported as "inode#" in /proc/pid/maps.
* proc-ps tools use this. Changing this will break them.
*/
file_inode(file)->i_ino = shp->shm_perm.id;
ns->shm_tot += numpages;
error = shp->shm_perm.id;
ipc_unlock_object(&shp->shm_perm);
rcu_read_unlock();
return error;
no_id:
ipc_update_pid(&shp->shm_cprid, NULL);
ipc_update_pid(&shp->shm_lprid, NULL);
fput(file);
ipc_rcu_putref(&shp->shm_perm, shm_rcu_free);
return error;
no_file:
call_rcu(&shp->shm_perm.rcu, shm_rcu_free);
return error;
}
/*
* Called with shm_ids.rwsem and ipcp locked.
*/
static int shm_more_checks(struct kern_ipc_perm *ipcp, struct ipc_params *params)
{
struct shmid_kernel *shp;
shp = container_of(ipcp, struct shmid_kernel, shm_perm);
if (shp->shm_segsz < params->u.size)
return -EINVAL;
return 0;
}
long ksys_shmget(key_t key, size_t size, int shmflg)
{
struct ipc_namespace *ns;
static const struct ipc_ops shm_ops = {
.getnew = newseg,
.associate = security_shm_associate,
.more_checks = shm_more_checks,
};
struct ipc_params shm_params;
ns = current->nsproxy->ipc_ns;
shm_params.key = key;
shm_params.flg = shmflg;
shm_params.u.size = size;
return ipcget(ns, &shm_ids(ns), &shm_ops, &shm_params);
}
SYSCALL_DEFINE3(shmget, key_t, key, size_t, size, int, shmflg)
{
return ksys_shmget(key, size, shmflg);
}
static inline unsigned long copy_shmid_to_user(void __user *buf, struct shmid64_ds *in, int version)
{
switch (version) {
case IPC_64:
return copy_to_user(buf, in, sizeof(*in));
case IPC_OLD:
{
struct shmid_ds out;
memset(&out, 0, sizeof(out));
ipc64_perm_to_ipc_perm(&in->shm_perm, &out.shm_perm);
out.shm_segsz = in->shm_segsz;
out.shm_atime = in->shm_atime;
out.shm_dtime = in->shm_dtime;
out.shm_ctime = in->shm_ctime;
out.shm_cpid = in->shm_cpid;
out.shm_lpid = in->shm_lpid;
out.shm_nattch = in->shm_nattch;
return copy_to_user(buf, &out, sizeof(out));
}
default:
return -EINVAL;
}
}
static inline unsigned long
copy_shmid_from_user(struct shmid64_ds *out, void __user *buf, int version)
{
switch (version) {
case IPC_64:
if (copy_from_user(out, buf, sizeof(*out)))
return -EFAULT;
return 0;
case IPC_OLD:
{
struct shmid_ds tbuf_old;
if (copy_from_user(&tbuf_old, buf, sizeof(tbuf_old)))
return -EFAULT;
out->shm_perm.uid = tbuf_old.shm_perm.uid;
out->shm_perm.gid = tbuf_old.shm_perm.gid;
out->shm_perm.mode = tbuf_old.shm_perm.mode;
return 0;
}
default:
return -EINVAL;
}
}
static inline unsigned long copy_shminfo_to_user(void __user *buf, struct shminfo64 *in, int version)
{
switch (version) {
case IPC_64:
return copy_to_user(buf, in, sizeof(*in));
case IPC_OLD:
{
struct shminfo out;
if (in->shmmax > INT_MAX)
out.shmmax = INT_MAX;
else
out.shmmax = (int)in->shmmax;
out.shmmin = in->shmmin;
out.shmmni = in->shmmni;
out.shmseg = in->shmseg;
out.shmall = in->shmall;
return copy_to_user(buf, &out, sizeof(out));
}
default:
return -EINVAL;
}
}
/*
* Calculate and add used RSS and swap pages of a shm.
* Called with shm_ids.rwsem held as a reader
*/
static void shm_add_rss_swap(struct shmid_kernel *shp,
unsigned long *rss_add, unsigned long *swp_add)
{
struct inode *inode;
inode = file_inode(shp->shm_file);
if (is_file_hugepages(shp->shm_file)) {
struct address_space *mapping = inode->i_mapping;
struct hstate *h = hstate_file(shp->shm_file);
*rss_add += pages_per_huge_page(h) * mapping->nrpages;
} else {
#ifdef CONFIG_SHMEM
struct shmem_inode_info *info = SHMEM_I(inode);
spin_lock_irq(&info->lock);
*rss_add += inode->i_mapping->nrpages;
*swp_add += info->swapped;
spin_unlock_irq(&info->lock);
#else
*rss_add += inode->i_mapping->nrpages;
#endif
}
}
/*
* Called with shm_ids.rwsem held as a reader
*/
static void shm_get_stat(struct ipc_namespace *ns, unsigned long *rss,
unsigned long *swp)
{
int next_id;
int total, in_use;
*rss = 0;
*swp = 0;
in_use = shm_ids(ns).in_use;
for (total = 0, next_id = 0; total < in_use; next_id++) {
struct kern_ipc_perm *ipc;
struct shmid_kernel *shp;
ipc = idr_find(&shm_ids(ns).ipcs_idr, next_id);
if (ipc == NULL)
continue;
shp = container_of(ipc, struct shmid_kernel, shm_perm);
shm_add_rss_swap(shp, rss, swp);
total++;
}
}
/*
* This function handles some shmctl commands which require the rwsem
* to be held in write mode.
* NOTE: no locks must be held, the rwsem is taken inside this function.
*/
static int shmctl_down(struct ipc_namespace *ns, int shmid, int cmd,
struct shmid64_ds *shmid64)
{
struct kern_ipc_perm *ipcp;
struct shmid_kernel *shp;
int err;
down_write(&shm_ids(ns).rwsem);
rcu_read_lock();